If I want to fine tune it for hindi, I would need to retrain tokenizer right? And it would start from scratch?
Amish
darknight054
AI & ML interests
None yet
Recent Activity
commented on
an
article
2 days ago
Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR
new activity
2 days ago
fixie-ai/ultravox-v0_7-glm-4_6:Hindi Support
new activity
19 days ago
google/medasr:Fine-tuning MedASR for Indian Regional Languages
Organizations
None yet